FPGA Realization of Deep Neural Network for Hardware Trojan Detection

Varun Reddy,Nirmala Devi M

doi:10.14419/ijet.v9i3.30946

Abstract

With the increase in outsourcing design and fabrication, malicious third-party vendors often insert hardware Trojan (HT) in the integrated Circuits(IC). It is difficult to identify these Trojans since the nature and characteristics of each Trojan differ significantly. Any method developed for HT detection is limited by its capacity on dealing with varied types of Trojans. The main purpose of this study is to show using deep learning (DL), this problem can be dealt with some extent and the effect of deep neural network (DNN) when it is realized on field programmable gate array (FPGA). In this paper, we propose a comparison of accuracy in finding faults on ISCAS’85 benchmark circuits between random forest classifier and DNN. Further for the faster processing time and less power consumption, the network is implemented on FPGA. The results show the performance of deep neural network gets better when a large number of nets are used and faster in the execution of the algorithm. Also, the speedup of the neuron is 100x times better when implemented on FPGA with 15.32% of resource utilization and provides less power consumption than GPU.

Highlights

With third party vendors inserting Trojans of different kinds which may cause a behavioral change in ICs or some secret information gets leaked
A subclass of machine learning (ML) that has the capability of choosing the parameters on its own has been chosen for this work as it provides better accuracy when dealing with complex circuits
Among the various kinds of research targeting the speed up of complex algorithms suitable choice is field programmable gate array(FPGA) which provides fast processing compared to general processing unit (GPU) [1] and cost-effective

Summary

Introduction

With third party vendors inserting Trojans of different kinds which may cause a behavioral change in ICs or some secret information gets leaked. The timing latency and power consumption are the major setbacks when this architecture is implemented in the general processing unit (GPU) To overcome this issue, this deep neural network (DNN) should be implemented on hardware. In [2], emerging attack modes and hardware Trojan attacks that are violating the trust of the consumer is analyzed in detail These Trojans inserted in different stages of hardware, different types of Trojan attacks on hardware, and the scenarios of the attacks are mentioned.[3]Presents an informatic-theoretic approach for Trojan detection. It evaluated the mathematical relationship among the signals in design and investigates how this evaluation can be done in a clustering algorithm to detect the Trojan logic.

Objectives

Findings

Discussion

Conclusion